{{ message }}
Repository navigation
fix(commands): give every command an imperative description - #726
Merged
Merged
Conversation
35 command files had no frontmatter, so `claude plugin validate --strict` failed with "No frontmatter block found" on the plugins that ship them. Each one now has a one-line `description:` written from the command body. Four commands reuse the wording of an identical command that already had one (refactor-clean, tech-debt, error-analysis, error-trace). The six descriptions added in #719 started with "Use when", which is the trigger style for skills. They now use the imperative style that every other command description uses, so the two identical context-restore copies read the same. No command body changes and no version bumps. Claude-Session: https://claude.ai/code/session_012TJthve8fGapk6u7aQg5iG
|
Navigate logical layers of code changes, visualize relationships, and explore their blast radius. No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Advanced Run ID: 📒 Files selected for processing (2)
🚧 Files skipped from review as they are similar to previous changes (2)
Included review availability: This review used your included allowance. Your plan provides up to 10 included reviews per hour; 3 remain after this review. 📜 Recent review details
|
| Layer / File(s) | Summary |
|---|---|
Add command descriptions plugins/*/commands/*.md |
New YAML frontmatter describes the scope and capabilities of commands across multiple plugins. |
Edit existing descriptions plugins/context-management/commands/*.md, plugins/debugging-toolkit/commands/smart-debug.md, plugins/dependency-management/commands/deps-audit.md, plugins/security-compliance/commands/compliance-check.md, plugins/security-scanning/commands/security-dependencies.md |
Existing descriptions have wording or punctuation changes. |
Priority: ➖ Normal
Estimated code review effort: 2 (Simple) | ~10 minutes
Change: Bug fix
Merge Risk: ⚪ Minimal · up to 98f3c
The description changes meet the checked-in command metadata contract; no actionable issue remains before merge.
Architecture Summary
Architecture risk: 🔵 Low · up to 3bb36
The change affects 1 system.
Changed systems: plugins
Architecture concerns
No architecture-level concerns identified.
Review details
Systems and components
- observed — plugins (service) was modified; 41 changed files map to changed impact.
Before / after behavior
- observed — Modified behavior in plugins/accessibility-compliance/commands/accessibility-audit.md: Added frontmatter with a description of the accessibility audit command.
- observed — Modified behavior in plugins/agent-orchestration/commands/improve-agent.md: Added YAML front matter with the command description and its performance-baseline, prompt-engineering, A/B-testing, and staged-rollout scope.
- observed — Modified behavior in plugins/agent-orchestration/commands/multi-agent-optimize.md: Added YAML frontmatter declaring the command’s description; the existing optimization-toolkit content is unchanged.
- observed — Modified behavior in plugins/api-testing-observability/commands/api-mock.md: Added YAML front matter with a description of the API mocking command.
🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
| Check name | Status | Explanation |
|---|---|---|
| Title check | ✅ Passed | The title clearly summarizes the main change: adding imperative descriptions to command metadata. |
| Description check | ✅ Passed | The description directly explains the frontmatter changes, validation issue, scope, and test results. |
| Docstring Coverage | ✅ Passed | No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Analyzed 0 functions across 0… |
| Linked Issues check | ✅ Passed | Check skipped because no linked issues were found for this pull request. |
| Out of Scope Changes check | ✅ Passed | Check skipped because no linked issues were found for this pull request. |
✨ Finishing Touches 💡 1
🛠️ Fix failing CI checks 💡
- Commit to this branch
- Create a new PR
🧪 Generate unit tests (beta)
- Commit to this branch
- Create a new PR
✨ Simplify code
- Commit to this branch
- Create a new PR
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.
A rabbit reads each command with care
New descriptions bloom here and there
YAML settles into place
Old words shift with measured grace
Then hops away, light as air
Comment @coderabbitai help to get the list of available commands.
Contributor
|
Claude encountered an error after 2m 32s —— View job Review: PR #726 — command frontmatter
No blocking issues. The two duplicate-drift findings from the previous review are fixed in What I verified:
One non-blocking nit:
I could not run |
13 of 21 tasks
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
![claude[bot]](https://avatars.githubusercontent.com/in/1236702?s=60&v=4){kind=small}
| @@ -1,5 +1,5 @@ | |||
| --- | |||
| description: Use when auditing dependencies for vulnerabilities, license compliance, and maintenance risks. | |||
| description: Audit dependencies for vulnerabilities, license compliance, and maintenance risks | |||
Contributor
There was a problem hiding this comment.
plugins/codebase-cleanup/commands/deps-audit.md is byte-identical to this file apart from line 2, so after this rewording the same command still ships two different descriptions — the same mismatch the PR fixes for context-restore.
-description: Audit dependencies for vulnerabilities, license compliance, and maintenance risks
+description: Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
Owner
Author
There was a problem hiding this comment.
Fixed in 98f3cdb. dependency-management/deps-audit now uses the same description as the copy in codebase-cleanup.
| @@ -1,5 +1,5 @@ | |||
| --- | |||
| description: Use when investigating an issue with debugging tools, observability data, and root cause analysis. | |||
| description: Investigate an issue with debugging tools, observability data, and root cause analysis | |||
Contributor
There was a problem hiding this comment.
Same duplicate-copy drift: plugins/error-diagnostics/commands/smart-debug.md has an identical body (only the subagent_type differs) but keeps "AI-assisted smart debugging — parse error messages, stack traces, and failure patterns…", so the two copies read differently after this change.
Owner
Author
There was a problem hiding this comment.
Fixed in 98f3cdb. debugging-toolkit/smart-debug now uses the same description as the copy in error-diagnostics. No other copy of the six commands differs.
dependency-management/deps-audit and debugging-toolkit/smart-debug have the same bodies as the copies in codebase-cleanup and error-diagnostics, which already had descriptions. Both now reuse that wording, so each duplicated command reads the same wherever it ships. Claude-Session: https://claude.ai/code/session_012TJthve8fGapk6u7aQg5iG
Owner
Author
|
@coderabbitai review |
3 of 4 tasks
wshobson
added a commit
that referenced
this pull request
Sep 25, 2026
…iew prompt (#729) * ci(claude): run both Claude workflows on Opus 5.5 and sharpen the review prompt Both workflows now run claude-opus-5-5 on claude-code-action v1.0.234. Opus 5.5 defaults to medium effort, so the review sets high and the @claude workflow sets xhigh for coding work. The review job failed on #726 and #728 because Claude finished in 31 turns against a limit of 30, so the limit is now 60. The review prompt now tells Claude that CI runs the gates and that it should read them with `gh pr checks`, since earlier reviews spent turns on commands the job can't run. It also checks the change against its linked issue, applies the commercial and external-service rules in CONTRIBUTING, skips findings that Codex already raised, and marks findings as blocking or not. The @claude workflow allows `uv` and `make` but never installed uv, so it now installs uv before running Claude. Claude-Session: https://claude.ai/code/session_012TJthve8fGapk6u7aQg5iG * ci(claude): let the reviewer read failed logs, review bodies, and issue comments The prompt asks the reviewer to name the gate that failed, but `gh pr checks` shows only check status, so the job can now run `gh run view --log-failed` with `actions: read`, and it requests `checks: read` for `gh pr checks`. The reviewer reads proposal issues with `--comments`, so it can see a maintainer answer, and it reads review bodies before it decides a finding is new. The commercial check now limits itself to runnable payment, licensing, or access-control machinery, which matches the exception in CONTRIBUTING. Claude-Session: https://claude.ai/code/session_012TJthve8fGapk6u7aQg5iG
3 tasks done
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
35 command files had no frontmatter, so
claude plugin validate --strictfailed with "No frontmatter block found" on the plugins that ship them. Each one now has a one-linedescription:written from the command body. Four commands reuse the wording of an identical command that already had a description (refactor-clean,tech-debt,error-analysis, anderror-trace).The six descriptions from #719 started with "Use when", which is the trigger style for skills. Four of them now use the imperative style that the other command descriptions use. The other two (
deps-auditandsmart-debug) reuse the description of an identical copy in another plugin, so every duplicated command reads the same wherever it ships.The change is metadata only, so no command body changes and no plugin version moves.
Scope
plugins/<name>/...)Test plan
claude plugin validate --strictpasses on all 25 plugins with new descriptions and on the 5 plugins from fix: describe six Claude plugin commands #719.plugins/*/commands/is left without frontmatter..codex,.opencode,.copilot,.antigravity, and.piloads withyaml.safe_load.make generate-allleaves no registry drift, andmake validate STRICT=1passes across 6 harnesses.make gardenreports 0 errors and 18 warnings, the same as main.make testpasses with 673 tests, andmake lintpasses.https://claude.ai/code/session_012TJthve8fGapk6u7aQg5iG